Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,878 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · Jul 201919922001200920172026
1 result for “AutoCompress”
AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Ratescs.LG

AutoCompress automatically prunes DNNs to ultra-high compression rates without accuracy loss.

problem Efficiently compressing deep neural networks to reduce storage and computation requirements.
method Automatic hyperparameter determination, ADMM-based structured weight pruning, purification step, heuristic search.
result Achieves ultra-high pruning rates on weights and FLOPs, up to 33x in pruning rate.
DNN compressionStructured pruningADMMAutoCompressInference speedup
2019-07-06abs ↗pdf ↗